tika-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Kranthi Kiran GV (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (TIKA-2322) Video labeling using existing ObjectRecognition
Date Wed, 12 Apr 2017 20:30:41 GMT

    [ https://issues.apache.org/jira/browse/TIKA-2322?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15966562#comment-15966562
] 

Kranthi Kiran GV commented on TIKA-2322:
----------------------------------------

OpenCV is available on the Central repository (https://search.maven.org/#artifactdetails%7Corg.bytedeco.javacpp-presets%7Copencv%7C3.2.0-1.3%7Cjar).
I believe the license of OpenCV would allow us to use it in the current proposal. (http://opencv.org/license.html)
They want us to include the copyright notice.




> Video labeling using existing ObjectRecognition
> -----------------------------------------------
>
>                 Key: TIKA-2322
>                 URL: https://issues.apache.org/jira/browse/TIKA-2322
>             Project: Tika
>          Issue Type: Improvement
>          Components: parser
>            Reporter: Madhav Sharan
>            Assignee: Chris A. Mattmann
>              Labels: memex
>             Fix For: 1.15
>
>
> Currently TIKA supports ObjectRecognition in Images. I am proposing to extend this to
support videos. 
> Idea is -
> 1. Extract frames from video and run IncV3 to get labels for these frames. 
> 2. We sum up confidence scores of each frame and label. 
> 3. Return results in sorted order of confidence score. 
> I am writing code for different modes of frame extractions -
> 1. Extract center image.
> 2. Extract frames after every fixed interval.
> 3. Extract N frames equally divided across video.
> We used this approach in [0]. Code in [1]
> [0] https://github.com/USCDataScience/hadoop-pot
> [1] https://github.com/USCDataScience/video-recognition



--
This message was sent by Atlassian JIRA
(v6.3.15#6346)

Mime
View raw message